Combines internalizing general skills with task-specific skill utilization via a difficulty-aware router to improve in-distribution and out-of-distribution performance for agentic RL. Uses privileged distillation for hard tasks and diagnostic probing for easy tasks; evaluated on ALFWorld and WebShop.
AI Agent Papers2026
Proposes TASTE, an automatic pipeline that synthesizes challenging agent benchmark tasks by sampling and evolving valid tool-sequence patterns; uses an adaptive contrastive n-gram model and LLM validity judgments to produce τ^c-Bench with broader tool-use coverage and higher difficulty.
AI Agent2026
Local-first AI agent workspace for authoring, running, and recovering agent executions — records model messages, tool calls, tool results, permission decisions, and termination events in an append-only Runtime Event Log. Provides Desktop (Electron), TUI/CLI, and headless Eval surfaces plus local tools and runtime features for pruning, compaction, and durable recovery.
AI Model2026
Hybrid LFM2.5 text-generation model optimized for on-device assistants and agentic workflows — 8.3B total / 1.5B active parameters with 131,072-token context. Prioritizes low-latency, high-throughput inference and multilingual instruction-following; not optimized for pure heavy programming or knowledge-heavy QA without retrieval.
AI Model2026
GGUF quantizations of Step-3.7-Flash: a sparse multimodal Mixture-of-Experts LLM with native image understanding, selectable reasoning levels, and a 256K context window. Ships multiple calibrated Q3/Q4/IQ quant files plus an mmproj vision projector for local llama.cpp inference on high-memory hosts.
AI Dataset2026
Provides a sanitized, MIT‑licensed dataset of scanner evidence and registry verdicts for public ClawHub agent skills — 67k+ latest skill versions with redacted artifacts and structured VirusTotal, static-analysis, and SkillSpector outputs to study scanner disagreement and agent-skill risk governance.
AI Agent Papers2026
Analyzes when masking stale observations improves long-horizon search agents and why, identifying an asymmetric inverted-U relationship between masking benefit, retriever quality, and model capacity; explains a token-for-turn trade-off and releases evaluation scaffolds and trajectories.
AI Agent Papers2026
Automates distillation of heterogeneous traces from a target person or role into versioned, inspectable skill packages for LLM agents — producing separate capability and bounded-behavior tracks that support natural-language corrections, rollback, and cross-host installation. Ships with an open system and a skills gallery.
AI Agent2026
Maintains a local, durable control-plane state that preserves objectives, typed todos, gates, evidence logs, quotas, and verifiable handoffs for long-running AI agent work. Designed to coordinate multi-day agent loops across Codex, Claude Code, Cursor or custom runners while keeping human judgment, auditability, and safe fallbacks explicit.
AI Agent2026
Turns terminal-agent CLIs you already run into a local desktop multi-agent harness: each agent runs as a real terminal process, with shared semantic memory, encrypted on-node messaging, a GOD orchestrator for routing/approvals, and a visual office floor for monitoring.
AI Agent Papers2026
Localizes harmful span-level errors inside long research-agent trajectories to show which trajectory segments make final answers unreliable. Provides a 1,000-instance TELBench of annotated spans and DRIFT, a claim-centric auditing method that improves span-level localization and first-error accuracy by up to 30 percentage points.
AI Dataset2026
Provides the gated, official OSWorld 2.0 Python task class files (task_*.py) required to run the benchmark; distributed via a Hugging Face gated dataset to reduce benchmark leakage. Download requires accepting gated access on Hugging Face.